From d7498093d0f5e0db052ef88815d57c2648d09425 Mon Sep 17 00:00:00 2001 From: lltommy Date: Thu, 9 Apr 2020 14:34:54 +0200 Subject: Updating schema and examples. This is still work in progress but we get there --- example/minimal_example.yaml | 14 ++++++++++++++ 1 file changed, 14 insertions(+) create mode 100644 example/minimal_example.yaml (limited to 'example/minimal_example.yaml') diff --git a/example/minimal_example.yaml b/example/minimal_example.yaml new file mode 100644 index 0000000..201b080 --- /dev/null +++ b/example/minimal_example.yaml @@ -0,0 +1,14 @@ +host: + host_id: XX + host_species: string + +sample: + collector_name: XXX + collecting_institution: XXX + +technology: + sample_sequencing_technology: XX + +submitter: + submitter_name: tester + originating_lab: testLab \ No newline at end of file -- cgit v1.2.3 From ddabd9390d2b221786ef58a6d85200eecf82ca2f Mon Sep 17 00:00:00 2001 From: lltommy Date: Fri, 10 Apr 2020 15:39:56 +0200 Subject: Updating schema and examples, including URIs --- bh20sequploader/bh20seq-schema.yml | 145 ++++++++++++++++++++++++++++++------- example/metadata.yaml | 4 + example/minimal_example.yaml | 6 +- 3 files changed, 128 insertions(+), 27 deletions(-) (limited to 'example/minimal_example.yaml') diff --git a/bh20sequploader/bh20seq-schema.yml b/bh20sequploader/bh20seq-schema.yml index 5c962d1..cf9b015 100644 --- a/bh20sequploader/bh20seq-schema.yml +++ b/bh20sequploader/bh20seq-schema.yml @@ -3,6 +3,10 @@ $namespaces: sch: https://schema.org/ efo: http://www.ebi.ac.uk/efo/ obo: http://purl.obolibrary.org/obo/ + sio: http://semanticscience.org/resource/ + edam: http://edamontology.org/ + evs: http://ncicb.nci.nih.gov/xml/owl/EVS/Thesaurus.owl# + $graph: - name: hostSchema @@ -12,37 +16,93 @@ $graph: type: string jsonldPredicate: _id: http://www.ebi.ac.uk/efo/EFO_0000532 - host_id: string - host_common_name: string? - host_sex: string? - host_age: int? - host_age_unit: string? - host_health_status: string? + host_id: + type: string + jsonldPredicate: + _id: http://semanticscience.org/resource/SIO_000115 + host_common_name: + type: string? + jsonldPredicate: + _id: http://purl.obolibrary.org/obo/NOMEN_0000037 + host_sex: + type: string + jsonldPredicate: + _id: http://purl.obolibrary.org/obo/PATO_0000047 + host_age: + type: int? + jsonldPredicate: + _id: http://purl.obolibrary.org/obo/PATO_0000011 + host_age_unit: + type: string? + jsonldPredicate: + _id: http://purl.obolibrary.org/obo/UO_0000036 + host_health_status: + type: string? + jsonldPredicate: http://purl.obolibrary.org/obo/NCIT_C25688 host_treatment: type: string? jsonldPredicate: _id: http://www.ebi.ac.uk/efo/EFO_0000727 - additional_host_information: string? + host_vaccination: + type: string? + jsonldPredicate: + _id: http://purl.obolibrary.org/obo/VO_0000001 + additional_host_information: + type: string? + jsonldPredicate: + _id: http://semanticscience.org/resource/SIO_001167 - name: sampleSchema type: record fields: - collector_name: string - collecting_institution: string - specimen_source: string? - collection_date: string? + collector_name: + type: string + jsonldPredicate: + _id: http://purl.obolibrary.org/obo/OBI_0001895 + collecting_institution: + type: string + jsonldPredicate: + _id: http://semanticscience.org/resource/SIO_001167 + specimen_source: + type: string? + jsonldPredicate: + _id: http://purl.obolibrary.org/obo/OBI_0001479 + collection_date: + type: string? + jsonldPredicate: + _id: http://ncicb.nci.nih.gov/xml/owl/EVS/Thesaurus.owl#C25164 collection_location: type: string? jsonldPredicate: - _id: https://schema.org/fromLocation - sample_storage_conditions: string? - additional_collection_information: string? + _id: http://purl.obolibrary.org/obo/GAZ_00000448 + sample_storage_conditions: + type: string? + jsonldPredicate: + _id: http://purl.obolibrary.org/obo/OBI_0001472 + additional_collection_information: + type: string? + jsonldPredicate: + _id: http://semanticscience.org/resource/SIO_001167 + sample_id: + type: string + jsonldPredicate: + _id: http://semanticscience.org/resource/SIO_000115 + source_database_accession: + type: string? + jsonldPredicate: + _id: http://edamontology.org/data_2091 - name: virusSchema type: record fields: - virus_species: string? - virus_strain: string? + virus_species: + type: string? + jsonldPredicate: + _id: http://edamontology.org/data_1875 + virus_strain: + type: string? + jsonldPredicate: + _id: http://semanticscience.org/resource/SIO_010055 - name: technologySchema type: record @@ -50,7 +110,7 @@ $graph: sample_sequencing_technology: type: string jsonldPredicate: - _id: http://www.ebi.ac.uk/efo/EFO_0000532 + _id: http://purl.obolibrary.org/obo/OBI_0600047 sequence_assembly_method: type: string? jsonldPredicate: @@ -63,14 +123,42 @@ $graph: - name: submitterSchema type: record fields: - submitter_name: string - submitter_address: string? - originating_lab: string - lab_address: string? - provider_sample_id: string? - submitter_sample_id: string? - authors: string? - submitter_id: string? + submitter_name: + type: string + jsonldPredicate: + _id: http://semanticscience.org/resource/SIO_000116 + submitter_date: + type: string + jsonldPredicate: + _id: http://purl.obolibrary.org/obo/NCIT_C94162 + submitter_address: + type: string? + jsonldPredicate: + _id: http://semanticscience.org/resource/SIO_000172 + originating_lab: + type: string + jsonldPredicate: + _id: http://purl.obolibrary.org/obo/NCIT_C37984 + lab_address: + type: string? + jsonldPredicate: + _id: http://purl.obolibrary.org/obo/OBI_0600047 + provider_sample_id: + type: string? + jsonldPredicate: + _id: http://purl.obolibrary.org/obo/NCIT_C37900 + submitter_sample_id: + type: string? + jsonldPredicate: + _id: http://www.ebi.ac.uk/efo/EFO_0001741 + authors: + type: string? + jsonldPredicate: + _id: http://purl.obolibrary.org/obo/NCIT_C42781 + submitter_id: + type: string? + jsonldPredicate: + _id: http://semanticscience.org/resource/SIO_000115 - name: MainSchema type: record @@ -81,9 +169,14 @@ $graph: virus: virusSchema? technology: technologySchema submitter: submitterSchema + submission: + type: string + jsonldPredicate: + _id: "@id" + #_type: "@id" sequencefile: doc: The subject (eg the fasta/fastq file) that this metadata describes type: string? jsonldPredicate: _id: "@id" - _type: "@id" + _type: "@id" \ No newline at end of file diff --git a/example/metadata.yaml b/example/metadata.yaml index 41ff93e..a2f6e57 100644 --- a/example/metadata.yaml +++ b/example/metadata.yaml @@ -1,3 +1,5 @@ +submission: publicSequenceResource + host: host_id: XX1 host_species: string @@ -10,6 +12,7 @@ host: additional_host_information: string sample: + sample_id: XXX collector_name: XXX collecting_institution: XXX specimen_source: XXX @@ -36,3 +39,4 @@ submitter: submitter_sample_id: string authors: testAuthor submitter_id: X12 + submitter_date: Subdate diff --git a/example/minimal_example.yaml b/example/minimal_example.yaml index 201b080..f312ab7 100644 --- a/example/minimal_example.yaml +++ b/example/minimal_example.yaml @@ -1,8 +1,11 @@ +submission: publicSequenceResource + host: host_id: XX host_species: string sample: + sample_id: XXX collector_name: XXX collecting_institution: XXX @@ -11,4 +14,5 @@ technology: submitter: submitter_name: tester - originating_lab: testLab \ No newline at end of file + originating_lab: testLab + submitter_date: Subdate \ No newline at end of file -- cgit v1.2.3 From 4f4229a61e63649730e7120c764f364078860f0f Mon Sep 17 00:00:00 2001 From: lltommy Date: Sat, 11 Apr 2020 02:44:04 +0200 Subject: Adding descriptions to the yml schema, slight changes to the yml schema --- bh20sequploader/bh20seq-schema.yml | 45 ++++++++++++++++++++++++++++++++------ example/metadata.yaml | 5 +++-- example/minimal_example.yaml | 6 ++--- 3 files changed, 44 insertions(+), 12 deletions(-) (limited to 'example/minimal_example.yaml') diff --git a/bh20sequploader/bh20seq-schema.yml b/bh20sequploader/bh20seq-schema.yml index 8a22db1..c259f16 100644 --- a/bh20sequploader/bh20seq-schema.yml +++ b/bh20sequploader/bh20seq-schema.yml @@ -13,41 +13,51 @@ $graph: type: record fields: host_species: + doc: Host species as defined in NCBITaxon (e.g. http://purl.obolibrary.org/obo/NCBITaxon_9606 for Homo sapiens) type: string jsonldPredicate: _id: http://www.ebi.ac.uk/efo/EFO_0000532 host_id: + doc: Identifer for the host. If you submit multiple samples from the same host, use the same host_id for those samples type: string jsonldPredicate: _id: http://semanticscience.org/resource/SIO_000115 host_common_name: + doc: Text label for the host species (e.g. homo sapiens) type: string? jsonldPredicate: _id: http://purl.obolibrary.org/obo/NOMEN_0000037 host_sex: + doc: Sex of the host as define in NCIT, IRI expected (http://purl.obolibrary.org/obo/C20197 (Male), http://purl.obolibrary.org/obo/NCIT_C27993 (Female) or unkown (http://purl.obolibrary.org/obo/NCIT_C17998)) type: string jsonldPredicate: _id: http://purl.obolibrary.org/obo/PATO_0000047 host_age: + doc: Age of the host as number (e.g. 50) type: int? jsonldPredicate: _id: http://purl.obolibrary.org/obo/PATO_0000011 host_age_unit: + doc: Unit of host age.... this field is unstable as of now (might be removed) type: string? jsonldPredicate: _id: http://purl.obolibrary.org/obo/UO_0000036 host_health_status: + doc: A condition or state at a particular time type: string? jsonldPredicate: http://purl.obolibrary.org/obo/NCIT_C25688 host_treatment: + doc: Process in which the act is intended to modify or alter type: string? jsonldPredicate: _id: http://www.ebi.ac.uk/efo/EFO_0000727 host_vaccination: + doc: Field is unstable type: string? jsonldPredicate: _id: http://purl.obolibrary.org/obo/VO_0000001 additional_host_information: + doc: Field for additional host information type: string? jsonldPredicate: _id: http://semanticscience.org/resource/SIO_001167 @@ -56,38 +66,47 @@ $graph: type: record fields: collector_name: + doc: Name of the person that took the sample type: string jsonldPredicate: _id: http://purl.obolibrary.org/obo/OBI_0001895 collecting_institution: + doc: Institute that was responsible of sampeling type: string jsonldPredicate: _id: http://semanticscience.org/resource/SIO_001167 specimen_source: + doc: A specimen that derives from an anatomical part or substance arising from an organism, e.g. tissue, organ type: string? jsonldPredicate: _id: http://purl.obolibrary.org/obo/OBI_0001479 collection_date: + doc: Date when the sample was taken type: string? jsonldPredicate: _id: http://ncicb.nci.nih.gov/xml/owl/EVS/Thesaurus.owl#C25164 collection_location: + doc: Geographical location where the sample was collected as Gazetteer (https://www.ebi.ac.uk/ols/ontologies/gaz) reference, e.g. http://purl.obolibrary.org/obo/GAZ_00002845 (China) type: string? jsonldPredicate: _id: http://purl.obolibrary.org/obo/GAZ_00000448 sample_storage_conditions: + doc: Information aboout storage of a specified type, e.g. frozen specimen, paraffin, fresh .... type: string? jsonldPredicate: _id: http://purl.obolibrary.org/obo/OBI_0001472 additional_collection_information: + doc: Add additional comment about the circumstances that a sample was taken type: string? jsonldPredicate: _id: http://semanticscience.org/resource/SIO_001167 sample_id: + doc: Id of the sample as defined by the submitter type: string jsonldPredicate: _id: http://semanticscience.org/resource/SIO_000115 source_database_accession: + doc: If data is deposit at a public resource (e.g. Genbank, ENA) enter the Accession Id here type: string? jsonldPredicate: _id: http://edamontology.org/data_2091 @@ -96,10 +115,12 @@ $graph: type: record fields: virus_species: + doc: The name of a taxon from the NCBI taxonomy database type: string? jsonldPredicate: _id: http://edamontology.org/data_1875 virus_strain: + doc: Name of the virus strain type: string? jsonldPredicate: _id: http://semanticscience.org/resource/SIO_010055 @@ -108,14 +129,17 @@ $graph: type: record fields: sample_sequencing_technology: + doc: Technology that was used to sequence this sample (e.g Sanger, Nanopor MiniION) type: string jsonldPredicate: _id: http://purl.obolibrary.org/obo/OBI_0600047 sequence_assembly_method: + doc: Protocol which provides instructions on the alignment of sequencing reads to reference genome type: string? jsonldPredicate: _id: http://www.ebi.ac.uk/efo/EFO_0002699 sequencing_coverage: + doc: Sequence coverage defined as the average number of reads representing a given nucleotide (e.g. 100x) type: string? jsonldPredicate: _id: http://purl.obolibrary.org/obo/FLU_0000848 @@ -124,22 +148,22 @@ $graph: type: record fields: submitter_name: + doc: Name of the submitter type: string jsonldPredicate: _id: http://semanticscience.org/resource/SIO_000116 - submitter_date: - type: string - jsonldPredicate: - _id: http://purl.obolibrary.org/obo/NCIT_C94162 submitter_address: + doc: Address of the submitter type: string? jsonldPredicate: _id: http://semanticscience.org/resource/SIO_000172 originating_lab: + doc: Name of the laboratory that took the sample type: string jsonldPredicate: _id: http://purl.obolibrary.org/obo/NCIT_C37984 lab_address: + doc: Address of the laboratory where the sample was taken type: string? jsonldPredicate: _id: http://purl.obolibrary.org/obo/OBI_0600047 @@ -152,10 +176,17 @@ $graph: jsonldPredicate: _id: http://www.ebi.ac.uk/efo/EFO_0001741 authors: + doc: Name of the author(s) type: string? jsonldPredicate: _id: http://purl.obolibrary.org/obo/NCIT_C42781 - submitter_id: + publication: + doc: Reference to publication of this sample (e.g. DOI, pubmed ID, ...) + type: string? + jsonldPredicate: + _id: http://purl.obolibrary.org/obo/NCIT_C19026 + submitter_orchid: + doc: ORCHID of the submitter type: string? jsonldPredicate: _id: http://semanticscience.org/resource/SIO_000115 @@ -171,7 +202,7 @@ $graph: submitter: submitterSchema id: doc: The subject (eg the fasta/fastq file) that the metadata describes - type: string? + type: string jsonldPredicate: _id: "@id" - _type: "@id" + #_type: "@id" # Error (contains undefined reference) if I keep this file but we need a toplevel id to tie things together diff --git a/example/metadata.yaml b/example/metadata.yaml index c780921..d9e8e92 100644 --- a/example/metadata.yaml +++ b/example/metadata.yaml @@ -1,3 +1,5 @@ +id: placeholder + host: host_id: XX1 host_species: string @@ -36,5 +38,4 @@ submitter: provider_sample_id: string submitter_sample_id: string authors: testAuthor - submitter_id: X12 - submitter_date: Subdate + submitter_orchid: X12 diff --git a/example/minimal_example.yaml b/example/minimal_example.yaml index f312ab7..160d1d4 100644 --- a/example/minimal_example.yaml +++ b/example/minimal_example.yaml @@ -1,8 +1,9 @@ -submission: publicSequenceResource +id: placeholder host: host_id: XX host_species: string + host_sex: string sample: sample_id: XXX @@ -14,5 +15,4 @@ technology: submitter: submitter_name: tester - originating_lab: testLab - submitter_date: Subdate \ No newline at end of file + originating_lab: testLab \ No newline at end of file -- cgit v1.2.3